Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:670d9d3e58c8e0a8f0f0efd81027ed2ceb60f0528fe900def47570a132365e02
+oid sha256:79bb69682b35346976c68d016a2b3c14cba1807de30549ce29f4697a260d32e5
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e52c8144ab9012854002a7e84157cbdaef067e32f02a5161c52757ebe5439421
+oid sha256:5a467aab0c2a8b2f1cabce4f011608e6436f364ec7412bad0f6fc9462e9643fd
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56cd1b84369114539ca2845260e4add78a7d5a16e84e599fb31c2f301b8ecb2e
+oid sha256:a1430d948d9499a27d1cfb1090b5a7b06287389a2b97c6dcf52e09078ca7f2e2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4d20cdfdd80bd4f7336e0d1d85ea3a727e6acd58210dc60f9f2cd451325f653
+oid sha256:e7f75dad5b4fa698adb63b89c53682112a536ec6b4f570bd7793123dfd2a0133
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1565217391304348,
+  "epoch": 0.3130434782608696,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 36.26,
       "eval_steps_per_second": 4.86,
       "step": 9
+    },
+    {
+      "epoch": 0.20869565217391303,
+      "grad_norm": 0.3947656452655792,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 1.7722,
+      "step": 12
+    },
+    {
+      "epoch": 0.2608695652173913,
+      "grad_norm": 0.4697956442832947,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 1.6984,
+      "step": 15
+    },
+    {
+      "epoch": 0.3130434782608696,
+      "grad_norm": 0.34927043318748474,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 1.7339,
+      "step": 18
+    },
+    {
+      "epoch": 0.3130434782608696,
+      "eval_loss": 1.4486348628997803,
+      "eval_runtime": 2.683,
+      "eval_samples_per_second": 36.153,
+      "eval_steps_per_second": 4.845,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2416597348122624.0,
+  "total_flos": 4767881254404096.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null